def ProgramSchedule(self): return program.SimpleProgramScheduleForTask( train_dataset_name='Train', train_steps_per_loop=50, eval_dataset_names=['Test'], eval_steps_per_loop=5, decode_steps_per_loop=0)
def ProgramSchedule(self): """Returns a schedule for the Executor.""" return program_lib.SimpleProgramScheduleForTask( 'Train', train_steps_per_loop=self.Task().train.tpu_steps_per_loop, eval_dataset_names=[], eval_steps_per_loop=0, decode_steps_per_loop=0)
def ProgramSchedule(self): # Only needed if --use_tpu_executor. p = program.SimpleProgramScheduleForTask(train_dataset_name='Train', train_steps_per_loop=1000, eval_dataset_names=[], eval_steps_per_loop=0, decode_steps_per_loop=0) p.train_executions_per_eval = 0 return p
def ProgramSchedule(self): return program.SimpleProgramScheduleForTask( train_dataset_name='Train', train_steps_per_loop=100, # I want to compute WER... eval_dataset_names=['Dev'], eval_steps_per_loop=1, decode_steps_per_loop=1, )
def ProgramSchedule(self): p = program.SimpleProgramScheduleForTask( train_dataset_name='Train', train_steps_per_loop=1000, eval_dataset_names=['Dev', 'Test'], eval_steps_per_loop=1, decode_steps_per_loop=1) p.train_executions_per_eval = 0 return p
def ProgramSchedule(self): p = program.SimpleProgramScheduleForTask( train_dataset_name='Train', train_steps_per_loop=train_steps_per_loop, eval_dataset_names=['Test'], eval_steps_per_loop=eval_decode_steps_per_loop, decode_steps_per_loop=eval_decode_steps_per_loop) if max_train_steps == 0: p.train_executions_per_eval = 0 return p
def ProgramSchedule(self): p = program.SimpleProgramScheduleForTask( train_dataset_name='Train', train_steps_per_loop=100, eval_dataset_names=['Train'], eval_steps_per_loop=100, decode_steps_per_loop=0, ) p.train_program.spmd = True # every 5K steps p.train_executions_per_eval = 5 return p
def ProgramSchedule(self): p = program.SimpleProgramScheduleForTask( train_dataset_name='Train', train_steps_per_loop=self.TRAIN_STEPS_PER_LOOP, eval_dataset_names=['Test'], eval_steps_per_loop=10, decode_steps_per_loop=0, ) p.train_program.spmd = True p.train_executions_per_eval = self.TRAIN_EXES_PER_EVAL # For compliance logging. p.ml_perf.benchmark_name = 'bert' p.ml_perf.submission_metadata = { 'global_batch_size': self.BATCH_SIZE, 'submission_org': 'Google', 'submission_platform': 'tpu-v4-4096', 'submission_division': 'open', 'submission_status': 'cloud', 'submission_benchmark': p.ml_perf.benchmark_name, 'submission_model': 'lingvo', 'cache_clear': None, 'train_samples': 156725653, 'eval_samples': 10000 } # For BERT, we log the number of examples as the epoch. # epoch_num = global_step / steps_per_epoch # epoch_num = num_examples_trained = global_step * examples_per_step # steps_per_epoch = global_step / (global_step * examples_per_step) # steps_per_epoch = 1 / examples_per_step examples_per_step = self.BATCH_SIZE p.ml_perf.steps_per_epoch = 1 / examples_per_step p.ml_perf.decoder_metric_name = 'acc1' p.ml_perf.decoder_metric_success_threshold = 0.6 p.ml_perf.max_steps_to_train = 31790 return p